A simple digits recognition neural network
Project description
Convolutional Neural Network using MNIST dataset for Digit Recognition
Official repository: https://github.com/MartinBraquet/ml-digits-recognition.
Test online: https://martinbraquet.com/index.php/solo_page_digits_recognition.
Installation from PyPI
pip install ml-digits-recognition
Usage
from ml_digits_recognition import drawing
drawing.run()
Installation from Source
pip install -r requirements.txt
Documentation
Convolutional neural network visualization.
nn_visualization.ipynb
Training
Train the model and save it as model.pt
.
ml_digits_recognition_training.ipynb
Accuracy vs epochs.
Loss vs epochs.
Test
Test in Jupiter Notebook. The model can be loaded from the training above in model.pt
or from the
default precise model in model_precise.pt
.
ml_digits_recognition_test.ipynb
Test in Python.
python drawing.py
Tools
Draw a digit and save it as a PNG file.
user_input_drawing.ipynb
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for ml_digits_recognition-0.0.3.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | f3ca463407962b06d45a05f0224239dc2f969c8644554cb0470d81e55d3df696 |
|
MD5 | 5557bbc12272203d14217ea08797b68f |
|
BLAKE2b-256 | aeafb09a2b0118b236194f8d4a3fc857dc643c57b422b2743eae37209720e28c |
Close
Hashes for ml_digits_recognition-0.0.3-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | cfc4878e7c88a38087f42bb2b2add4ab561ec9ce5a1933fbfba7f91808fb6674 |
|
MD5 | 0b3a99c0a5cb54e2768099ec7bb8ab3f |
|
BLAKE2b-256 | 44dbb44ca3676c22f58815f3f87ecf5e1e8ce907330e100f679750db7223833a |